speconsense 0.7.2__py3-none-any.whl → 0.7.4__py3-none-any.whl

speconsense/__init__.py

@@ -5,7 +5,7 @@ A Python tool for experimental clustering and consensus generation as an alterna
 in the fungal DNA barcoding pipeline.
 """
 
-__version__ = "0.7.2"
+__version__ = "0.7.4"
 __author__ = "Josh Walker"
 __email__ = "joshowalker@yahoo.com"
 

speconsense/core/cli.py

@@ -66,6 +66,9 @@ def main():
                                help="Disable position-based variant phasing (enabled by default). "
                                     "MCL graph clustering already separates most variants; this "
                                     "second pass analyzes MSA positions to phase remaining variants.")
+    phasing_group.add_argument("--enable-position-phasing", action="store_false",
+                               dest="disable_position_phasing",
+                               help="Override --disable-position-phasing or profile setting")
     phasing_group.add_argument("--min-variant-frequency", type=float, default=0.10,
                                help="Minimum alternative allele frequency to call variant (default: 0.10 for 10%%)")
     phasing_group.add_argument("--min-variant-count", type=int, default=5,
@@ -75,6 +78,9 @@ def main():
     ambiguity_group = parser.add_argument_group("Ambiguity Calling")
     ambiguity_group.add_argument("--disable-ambiguity-calling", action="store_true",
                                  help="Disable IUPAC ambiguity code calling for unphased variant positions")
+    ambiguity_group.add_argument("--enable-ambiguity-calling", action="store_false",
+                                 dest="disable_ambiguity_calling",
+                                 help="Override --disable-ambiguity-calling or profile setting")
     ambiguity_group.add_argument("--min-ambiguity-frequency", type=float, default=0.10,
                                  help="Minimum alternative allele frequency for IUPAC ambiguity calling (default: 0.10 for 10%%)")
     ambiguity_group.add_argument("--min-ambiguity-count", type=int, default=3,
@@ -84,8 +90,14 @@ def main():
     merging_group = parser.add_argument_group("Cluster Merging")
     merging_group.add_argument("--disable-cluster-merging", action="store_true",
                                help="Disable merging of clusters with identical consensus sequences")
+    merging_group.add_argument("--enable-cluster-merging", action="store_false",
+                               dest="disable_cluster_merging",
+                               help="Override --disable-cluster-merging or profile setting")
     merging_group.add_argument("--disable-homopolymer-equivalence", action="store_true",
                                help="Disable homopolymer equivalence in cluster merging (only merge identical sequences)")
+    merging_group.add_argument("--enable-homopolymer-equivalence", action="store_false",
+                               dest="disable_homopolymer_equivalence",
+                               help="Override --disable-homopolymer-equivalence or profile setting")
 
     # Orientation group
     orient_group = parser.add_argument_group("Orientation")
@@ -104,11 +116,17 @@ def main():
                                  "0=auto-detect, default=1 (safe for parallel workflows).")
     perf_group.add_argument("--enable-early-filter", action="store_true",
                             help="Enable early filtering to skip small clusters before variant phasing (improves performance for large datasets)")
+    perf_group.add_argument("--disable-early-filter", action="store_false",
+                            dest="enable_early_filter",
+                            help="Override --enable-early-filter or profile setting")
 
     # Debugging group
     debug_group = parser.add_argument_group("Debugging")
     debug_group.add_argument("--collect-discards", action="store_true",
                              help="Write discarded reads (outliers and filtered clusters) to cluster_debug/{sample}-discards.fastq")
+    debug_group.add_argument("--no-collect-discards", action="store_false",
+                             dest="collect_discards",
+                             help="Override --collect-discards or profile setting")
     debug_group.add_argument("--log-level", default="INFO",
                              choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"])
 

speconsense/profiles/__init__.py

@@ -103,6 +103,8 @@ VALID_SUMMARIZE_KEYS = {
     "select-max-groups",
     "select-max-variants",
     "select-strategy",
+    "select-min-size-ratio",
+    "enable-full-consensus",
     # Processing
     "scale-threshold",
     "threads",

speconsense/profiles/compressed.yaml

@@ -0,0 +1,28 @@
+# Compress variants into minimal IUPAC consensus sequences
+#
+# Aggressively merges similar variants (including indels) into single
+# IUPAC consensus sequences. Only truly dissimilar sequences remain
+# separate. Uses 20% frequency thresholds throughout.
+#
+# Designed for workflows where reviewers want fewer sequences to
+# examine, with all variation represented via IUPAC ambiguity codes.
+# Partial overlap merging is disabled as a safety measure.
+#
+# Use with:
+#   speconsense input.fastq -p compressed
+#   speconsense-summarize -p compressed
+
+speconsense-version: "0.7.*"
+description: "Compress variants into minimal IUPAC consensus sequences"
+
+speconsense:
+  min-ambiguity-frequency: 0.20  # 20% threshold for IUPAC ambiguity calling
+  min-variant-frequency: 0.20   # 20% threshold for variant phasing
+
+speconsense-summarize:
+  merge-indel-length: 5         # Merge indels up to 5bp
+  merge-position-count: 10      # Allow up to 10 variant positions in a merge
+  merge-min-size-ratio: 0.2     # Match 20% calling threshold
+  select-min-size-ratio: 0.2    # Match 20% calling threshold
+  min-merge-overlap: 0          # Disable partial overlap merging
+  enable-full-consensus: true   # Include full IUPAC consensus per group

speconsense/profiles/example.yaml

@@ -91,6 +91,7 @@ speconsense-summarize:
   # select-max-groups: -1         # Max groups to output (-1 = no limit)
   # select-max-variants: -1       # Max variants per group (-1 = no limit)
   # select-strategy: size         # Selection strategy: size or diversity
+  # select-min-size-ratio: 0    # Min size ratio to include variant (0 = disabled)
 
   # --- Processing ---
   # threads: 0                    # Max threads (0 = auto-detect)

speconsense/summarize/cli.py

@@ -54,8 +54,8 @@ from .io import (
     write_output_files,
 )
 from .clustering import perform_hac_clustering, select_variants
-from .merging import merge_group_with_msa
-from .analysis import MAX_MSA_MERGE_VARIANTS, MIN_MERGE_BATCH, MAX_MERGE_BATCH
+from .merging import merge_group_with_msa, create_full_consensus_from_msa
+from .analysis import run_spoa_msa, MAX_MSA_MERGE_VARIANTS, MIN_MERGE_BATCH, MAX_MERGE_BATCH
 
 
 # Merge effort configuration
@@ -132,6 +132,8 @@ def parse_arguments():
     merging_group = parser.add_argument_group("Merging")
     merging_group.add_argument("--disable-merging", action="store_true",
                                help="Disable all variant merging (skip MSA-based merge evaluation entirely)")
+    merging_group.add_argument("--enable-merging", action="store_false", dest="disable_merging",
+                               help="Override --disable-merging or profile setting")
     merging_group.add_argument("--merge-snp", action=argparse.BooleanOptionalAction, default=True,
                                help="Enable SNP-based merging (default: True, use --no-merge-snp to disable)")
     merging_group.add_argument("--merge-indel-length", type=int, default=0,
@@ -144,6 +146,9 @@ def parse_arguments():
                                help="Minimum overlap in bp for merging sequences of different lengths (default: 200, 0 to disable)")
     merging_group.add_argument("--disable-homopolymer-equivalence", action="store_true",
                                help="Disable homopolymer equivalence in merging (treat AAA vs AAAA as different)")
+    merging_group.add_argument("--enable-homopolymer-equivalence", action="store_false",
+                               dest="disable_homopolymer_equivalence",
+                               help="Override --disable-homopolymer-equivalence or profile setting")
     merging_group.add_argument("--merge-effort", type=str, default="balanced", metavar="LEVEL",
                                help="Merging effort level: fast (8), balanced (10), thorough (12), "
                                     "or numeric 6-14. Higher values allow larger batch sizes for "
@@ -164,6 +169,15 @@ def parse_arguments():
     selection_group.add_argument("--select-strategy", "--variant-selection",
                                  dest="select_strategy", choices=["size", "diversity"], default="size",
                                  help="Variant selection strategy: size or diversity (default: size)")
+    selection_group.add_argument("--select-min-size-ratio", type=float, default=0,
+                                 help="Minimum size ratio (variant/largest) to include in output "
+                                      "(default: 0 = disabled, e.g. 0.2 for 20%% cutoff)")
+    selection_group.add_argument("--enable-full-consensus", action="store_true",
+                                 help="Generate a full consensus per variant group representing all variation "
+                                      "from pre-merge variants (gaps never win)")
+    selection_group.add_argument("--disable-full-consensus", action="store_false",
+                                 dest="enable_full_consensus",
+                                 help="Override --enable-full-consensus or profile setting")
 
     # Performance group
     perf_group = parser.add_argument_group("Performance")
@@ -345,9 +359,21 @@ def process_single_specimen(file_consensuses: List[ConsensusInfo],
                           key=lambda x: max(m.size for m in x[1]),
                           reverse=True)
 
-    for group_idx, (_, group_members) in enumerate(sorted_groups):
+    for group_idx, (group_id, group_members) in enumerate(sorted_groups):
         final_group_name = group_idx + 1
 
+        # Apply select-min-size-ratio filter
+        if args.select_min_size_ratio > 0 and len(group_members) > 1:
+            largest_size = max(v.size for v in group_members)
+            filtered = [v for v in group_members
+                        if (v.size / largest_size) >= args.select_min_size_ratio]
+            if len(filtered) < len(group_members):
+                filtered_count = len(group_members) - len(filtered)
+                logging.debug(f"Group {group_idx + 1}: filtered out {filtered_count} "
+                              f"variants with size ratio < {args.select_min_size_ratio} "
+                              f"relative to largest (size={largest_size})")
+                group_members = filtered
+
         # Select variants for this group
         selected_variants = select_variants(group_members, args.select_max_variants, args.select_strategy, group_number=final_group_name)
 
@@ -366,6 +392,35 @@ def process_single_specimen(file_consensuses: List[ConsensusInfo],
             final_consensus.append(renamed_variant)
             group_naming.append((variant.sample_name, new_name))
 
+        # Generate full consensus from PRE-MERGE variants
+        if getattr(args, 'enable_full_consensus', False):
+            pre_merge_variants = variant_groups[group_id]
+
+            # Apply size-ratio filter (same as merge pipeline)
+            if args.merge_min_size_ratio > 0 and len(pre_merge_variants) > 1:
+                largest_size = max(v.size for v in pre_merge_variants)
+                filtered = [v for v in pre_merge_variants
+                            if (v.size / largest_size) >= args.merge_min_size_ratio]
+                if len(filtered) < len(pre_merge_variants):
+                    filtered_count = len(pre_merge_variants) - len(filtered)
+                    logging.debug(f"Full consensus: filtered out {filtered_count} variants with size ratio < {args.merge_min_size_ratio} relative to largest (size={largest_size})")
+                    pre_merge_variants = filtered
+
+            specimen_base = selected_variants[0].sample_name.rsplit('-c', 1)[0]
+            full_name = f"{specimen_base}-{group_idx + 1}.full"
+
+            if len(pre_merge_variants) == 1:
+                # Single variant — copy directly
+                full_consensus = pre_merge_variants[0]._replace(sample_name=full_name)
+            else:
+                # MSA on pre-merge variants, full consensus logic
+                sequences = [v.sequence for v in pre_merge_variants]
+                aligned_seqs = run_spoa_msa(sequences, alignment_mode=1)
+                full_consensus = create_full_consensus_from_msa(aligned_seqs, pre_merge_variants)
+                full_consensus = full_consensus._replace(sample_name=full_name)
+
+            final_consensus.append(full_consensus)
+
         naming_info[group_idx + 1] = group_naming
 
     logging.info(f"Processed {file_name}: {len(final_consensus)} final variants across {len(merged_groups)} groups")
@@ -421,6 +476,8 @@ def main():
     logging.info(f"  --select-max-variants: {args.select_max_variants}")
     logging.info(f"  --select-max-groups: {args.select_max_groups}")
     logging.info(f"  --select-strategy: {args.select_strategy}")
+    logging.info(f"  --select-min-size-ratio: {args.select_min_size_ratio}")
+    logging.info(f"  --enable-full-consensus: {args.enable_full_consensus}")
     logging.info(f"  --log-level: {args.log_level}")
     logging.info("")
     logging.info("Processing each specimen file independently to organize variants within specimens")

speconsense/summarize/fields.py

@@ -124,8 +124,8 @@ class GroupField(FastaField):
         super().__init__('group', 'Variant group number')
 
     def format_value(self, consensus: ConsensusInfo) -> Optional[str]:
-        # Extract from sample_name (e.g., "...-1.v1" or "...-2.v1.raw1")
-        match = re.search(r'-(\d+)\.v\d+(?:\.raw\d+)?$', consensus.sample_name)
+        # Extract from sample_name (e.g., "...-1.v1", "...-2.v1.raw1", or "...-1.full")
+        match = re.search(r'-(\d+)(?:\.v\d+(?:\.raw\d+)?|\.full)$', consensus.sample_name)
         if match:
             return f"group={match.group(1)}"
         return None
@@ -136,8 +136,10 @@ class VariantField(FastaField):
         super().__init__('variant', 'Variant identifier within group')
 
     def format_value(self, consensus: ConsensusInfo) -> Optional[str]:
-        # Extract from sample_name (e.g., "...-1.v1" -> "v1" or "...-1.v1.raw1" -> "v1")
+        # Extract from sample_name (e.g., "...-1.v1" -> "v1", "...-1.v1.raw1" -> "v1", "...-1.full" -> "full")
         match = re.search(r'\.(v\d+)(?:\.raw\d+)?$', consensus.sample_name)
+        if not match:
+            match = re.search(r'\.(full)$', consensus.sample_name)
         if match:
             return f"variant={match.group(1)}"
         return None

speconsense/summarize/io.py

@@ -358,6 +358,9 @@ def write_specimen_data_files(specimen_consensus: List[ConsensusInfo],
     # Generate .raw file consensuses for merged variants
     raw_file_consensuses = []
     for consensus in specimen_consensus:
+        # Skip .raw generation for .full consensus (synthetic/derived)
+        if consensus.sample_name.endswith('.full'):
+            continue
         # Only create .raw files if this consensus was actually merged
         if consensus.raw_ric and len(consensus.raw_ric) > 1:
             # Find the original cluster name from naming_info
@@ -412,6 +415,9 @@ def write_specimen_data_files(specimen_consensus: List[ConsensusInfo],
 
     # Write FASTQ files for each final consensus containing all contributing reads
     for consensus in specimen_consensus:
+        # Skip FASTQ for .full consensus (synthetic/derived, no traceable cluster reads)
+        if consensus.sample_name.endswith('.full'):
+            continue
         write_consensus_fastq(consensus, merge_traceability, naming_info, fastq_dir, fastq_lookup, original_consensus_lookup)
 
     # Write .raw files (individual FASTA and FASTQ for pre-merge variants)
@@ -704,7 +710,10 @@ def write_output_files(final_consensus: List[ConsensusInfo],
             multiple_id = specimen_counters[base_name]
             writer.writerow([consensus.sample_name, len(consensus.sequence), consensus.ric, multiple_id])
             unique_samples.add(base_name)
-            total_ric += consensus.ric
+            # Exclude .full from total RiC to avoid double-counting
+            # (.full aggregates reads already counted in merged variants)
+            if not consensus.sample_name.endswith('.full'):
+                total_ric += consensus.ric
 
         writer.writerow([])
         writer.writerow(['Total Unique Samples', len(unique_samples)])

speconsense/summarize/merging.py

@@ -106,6 +106,63 @@ def is_compatible_subset(variant_stats: dict, args, prior_positions: dict = None
     return True
 
 
+def _build_merged_consensus_info(
+    consensus_seq: list, snp_count: int, variants: List[ConsensusInfo]
+) -> ConsensusInfo:
+    """Assemble a ConsensusInfo from column-voting results and source variants.
+
+    Handles joining the consensus sequence, aggregating size/ric totals,
+    flattening raw_ric/raw_len merge history, and selecting metadata
+    from the largest variant.
+
+    Args:
+        consensus_seq: List of consensus characters from column voting
+        snp_count: Number of ambiguous (multi-base) positions
+        variants: Source ConsensusInfo objects that were merged
+
+    Returns:
+        ConsensusInfo with merged metadata
+    """
+    consensus_sequence = ''.join(consensus_seq)
+    total_size = sum(v.size for v in variants)
+    total_ric = sum(v.ric for v in variants)
+
+    # Collect RiC values, preserving any prior merge history
+    raw_ric_values = []
+    for v in variants:
+        if v.raw_ric:
+            raw_ric_values.extend(v.raw_ric)
+        else:
+            raw_ric_values.append(v.ric)
+    raw_ric_values = sorted(raw_ric_values, reverse=True) if len(variants) > 1 else None
+
+    # Collect lengths, preserving any prior merge history
+    raw_len_values = []
+    for v in variants:
+        if v.raw_len:
+            raw_len_values.extend(v.raw_len)
+        else:
+            raw_len_values.append(len(v.sequence))
+    raw_len_values = sorted(raw_len_values, reverse=True) if len(variants) > 1 else None
+
+    largest_variant = max(variants, key=lambda v: v.size)
+
+    return ConsensusInfo(
+        sample_name=largest_variant.sample_name,
+        cluster_id=largest_variant.cluster_id,
+        sequence=consensus_sequence,
+        ric=total_ric,
+        size=total_size,
+        file_path=largest_variant.file_path,
+        snp_count=snp_count if snp_count > 0 else None,
+        primers=largest_variant.primers,
+        raw_ric=raw_ric_values,
+        raw_len=raw_len_values,
+        rid=largest_variant.rid,
+        rid_min=largest_variant.rid_min,
+    )
+
+
 def create_consensus_from_msa(aligned_seqs: List, variants: List[ConsensusInfo]) -> ConsensusInfo:
     """
     Generate consensus from MSA using size-weighted majority voting.
@@ -160,46 +217,7 @@ def create_consensus_from_msa(aligned_seqs: List, variants: List[ConsensusInfo])
                 snp_count += 1
         # else: majority wants gap, omit position
 
-    # Create merged ConsensusInfo
-    consensus_sequence = ''.join(consensus_seq)
-    total_size = sum(v.size for v in variants)
-    total_ric = sum(v.ric for v in variants)
-
-    # Collect RiC values, preserving any prior merge history
-    raw_ric_values = []
-    for v in variants:
-        if v.raw_ric:
-            raw_ric_values.extend(v.raw_ric)  # Flatten prior merge history
-        else:
-            raw_ric_values.append(v.ric)
-    raw_ric_values = sorted(raw_ric_values, reverse=True) if len(variants) > 1 else None
-
-    # Collect lengths, preserving any prior merge history
-    raw_len_values = []
-    for v in variants:
-        if v.raw_len:
-            raw_len_values.extend(v.raw_len)  # Flatten prior merge history
-        else:
-            raw_len_values.append(len(v.sequence))
-    raw_len_values = sorted(raw_len_values, reverse=True) if len(variants) > 1 else None
-
-    # Use name from largest variant
-    largest_variant = max(variants, key=lambda v: v.size)
-
-    return ConsensusInfo(
-        sample_name=largest_variant.sample_name,
-        cluster_id=largest_variant.cluster_id,
-        sequence=consensus_sequence,
-        ric=total_ric,
-        size=total_size,
-        file_path=largest_variant.file_path,
-        snp_count=snp_count if snp_count > 0 else None,
-        primers=largest_variant.primers,
-        raw_ric=raw_ric_values,
-        raw_len=raw_len_values,
-        rid=largest_variant.rid,  # Preserve identity metrics from largest variant
-        rid_min=largest_variant.rid_min,
-    )
+    return _build_merged_consensus_info(consensus_seq, snp_count, variants)
 
 
 def create_overlap_consensus_from_msa(aligned_seqs: List, variants: List[ConsensusInfo]) -> ConsensusInfo:
@@ -295,46 +313,49 @@ def create_overlap_consensus_from_msa(aligned_seqs: List, variants: List[Consens
                     consensus_seq.append(iupac_code)
                     snp_count += 1
 
-    # Create merged ConsensusInfo
-    consensus_sequence = ''.join(consensus_seq)
-    total_size = sum(v.size for v in variants)
-    total_ric = sum(v.ric for v in variants)
+    return _build_merged_consensus_info(consensus_seq, snp_count, variants)
 
-    # Collect RiC values, preserving any prior merge history
-    raw_ric_values = []
-    for v in variants:
-        if v.raw_ric:
-            raw_ric_values.extend(v.raw_ric)  # Flatten prior merge history
-        else:
-            raw_ric_values.append(v.ric)
-    raw_ric_values = sorted(raw_ric_values, reverse=True) if len(variants) > 1 else None
 
-    # Collect lengths, preserving any prior merge history
-    raw_len_values = []
-    for v in variants:
-        if v.raw_len:
-            raw_len_values.extend(v.raw_len)  # Flatten prior merge history
-        else:
-            raw_len_values.append(len(v.sequence))
-    raw_len_values = sorted(raw_len_values, reverse=True) if len(variants) > 1 else None
+def create_full_consensus_from_msa(aligned_seqs: List, variants: List[ConsensusInfo]) -> ConsensusInfo:
+    """
+    Generate full consensus from MSA where any non-gap base means inclusion.
 
-    # Use name from largest variant
-    largest_variant = max(variants, key=lambda v: v.size)
+    Unlike create_consensus_from_msa where gaps can win by majority vote,
+    the full consensus includes a position if ANY variant has a base there.
+    This captures all variation from all contributing variants.
 
-    return ConsensusInfo(
-        sample_name=largest_variant.sample_name,
-        cluster_id=largest_variant.cluster_id,
-        sequence=consensus_sequence,
-        ric=total_ric,
-        size=total_size,
-        file_path=largest_variant.file_path,
-        snp_count=snp_count if snp_count > 0 else None,
-        primers=largest_variant.primers,
-        raw_ric=raw_ric_values,
-        raw_len=raw_len_values,
-        rid=largest_variant.rid,
-        rid_min=largest_variant.rid_min,
-    )
+    Args:
+        aligned_seqs: MSA sequences with gaps as '-'
+        variants: Original ConsensusInfo objects (for metadata)
+
+    Returns:
+        ConsensusInfo with full consensus sequence
+    """
+    consensus_seq = []
+    snp_count = 0
+    alignment_length = len(aligned_seqs[0].seq)
+
+    for col_idx in range(alignment_length):
+        column = [str(seq.seq[col_idx]) for seq in aligned_seqs]
+
+        # Collect non-gap bases
+        base_votes = defaultdict(int)
+        for i, base in enumerate(column):
+            upper_base = base.upper()
+            if upper_base != '-':
+                base_votes[upper_base] += variants[i].size
+
+        # Include position if ANY variant has a base (gaps never win)
+        if base_votes:
+            if len(base_votes) == 1:
+                consensus_seq.append(list(base_votes.keys())[0])
+            else:
+                represented_bases = set(base_votes.keys())
+                iupac_code = merge_bases_to_iupac(represented_bases)
+                consensus_seq.append(iupac_code)
+                snp_count += 1
+
+    return _build_merged_consensus_info(consensus_seq, snp_count, variants)
 
 
 def merge_group_with_msa(variants: List[ConsensusInfo], args) -> Tuple[List[ConsensusInfo], Dict, int, List[OverlapMergeInfo]]:

{speconsense-0.7.2.dist-info → speconsense-0.7.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: speconsense
-Version: 0.7.2
+Version: 0.7.4
 Summary: High-quality clustering and consensus generation for Oxford Nanopore amplicon reads
 Author-email: Josh Walker <joshowalker@yahoo.com>
 License: BSD-3-Clause
@@ -171,6 +171,7 @@ speconsense input.fastq -p herbarium --min-size 10
 ```
 
 **Bundled profiles:**
+- `compressed` — Compress variants into minimal IUPAC consensus sequences (aggressive merging with indels, 20% thresholds, full consensus, 20% selection size ratio)
 - `herbarium` — High-recall for degraded DNA/type specimens
 - `largedata` — Experimental settings for large input files
 - `nostalgia` — Simulate older bioinformatics pipelines
@@ -294,12 +295,14 @@ When using `speconsense-summarize` for post-processing, creates `__Summary__/` d
 |---------------|-------------|------------|-------------|
 | **Original** | Source `cluster_debug/` | `-c1`, `-c2`, `-c3` | Preserves speconsense clustering results |
 | **Summarization** | `__Summary__/`, `FASTQ Files/`, `variants/` | `-1.v1`, `-1.v2`, `-2.v1`, `.raw1` | Post-processing groups and variants |
+| **Full consensus** | `__Summary__/` | `-1.full` | IUPAC consensus from all pre-merge variants in a group |
 
 ### Example Directory Structure
 ```
 __Summary__/
 ├── sample-1.v1-RiC45.fasta                  # Primary variant (group 1, merged)
 ├── sample-1.v2-RiC23.fasta                  # Additional variant (not merged)
+├── sample-1.full-RiC68.fasta                # Full IUPAC consensus for group 1 (all pre-merge variants)
 ├── sample-2.v1-RiC30.fasta                  # Second organism group, primary variant
 ├── summary.fasta                            # All final consensus sequences (excludes .raw)
 ├── summary.txt                              # Statistics
@@ -675,6 +678,18 @@ speconsense-summarize --select-strategy diversity --select-max-variants 2
    - Output up to select_max_variants per group
 3. Final output contains representatives from all groups, ensuring both biological diversity (between groups) and appropriate sampling within each biological entity (within groups)
 
+**Selection Size Ratio Filtering:**
+```bash
+speconsense-summarize --select-min-size-ratio 0.2
+```
+- Filters out post-merge variants whose size is too small relative to the largest variant in their group
+- Ratio calculated as `variant_size / largest_size` — must be ≥ threshold to keep
+- Example: `--select-min-size-ratio 0.2` means a variant must have ≥20% the reads of the largest variant in its group
+- Default is 0 (disabled) — all post-merge variants pass through to selection
+- Applied after merging but before variant selection
+- Useful for suppressing noise variants that survived merging but are too small to be meaningful
+- Set to 0.2 in the `compressed` profile to match the 20% calling threshold theme
+
 This two-stage process ensures that distinct biological sequences are preserved as separate groups, while providing control over variant complexity within each group.
 
 ### Customizing FASTA Header Fields
@@ -810,6 +825,18 @@ For high-throughput workflows (e.g., 100K sequences/year), this prioritization e
 
 ### Additional Summarize Options
 
+**Full Consensus:**
+```bash
+speconsense-summarize --enable-full-consensus
+```
+- Generates a full IUPAC consensus sequence per variant group from all pre-merge variants
+- Output named `{specimen}-{group}.full-RiC{reads}.fasta` in the `__Summary__/` directory
+- Uses majority voting across all variants in the group; **gaps never win** — at each alignment column, the most common non-gap base is chosen, with IUPAC codes for ties among bases
+- Useful when you want a single representative sequence that captures all variation within a group as IUPAC ambiguity codes
+- Included in `summary.fasta` (but excluded from total RiC to avoid double-counting)
+- Enabled by default in the `compressed` profile
+- Use `--disable-full-consensus` to override when set by a profile
+
 **Quality Filtering:**
 ```bash
 speconsense-summarize --min-ric 5
@@ -1044,8 +1071,10 @@ The complete speconsense-summarize workflow operates in this order:
 2. **HAC variant grouping** by sequence identity to separate dissimilar sequences (`--group-identity`); uses single-linkage when overlap merging is enabled
 3. **Group filtering** to limit output groups (`--select-max-groups`)
 4. **Homopolymer-aware MSA-based variant merging** within each group, including **overlap merging** for different-length sequences (`--disable-merging`, `--merge-effort`, `--merge-position-count`, `--merge-indel-length`, `--min-merge-overlap`, `--merge-snp`, `--merge-min-size-ratio`, `--disable-homopolymer-equivalence`)
-5. **Variant selection** within each group (`--select-max-variants`, `--select-strategy`)
-6. **Output generation** with customizable header fields (`--fasta-fields`) and full traceability
+5. **Selection size ratio filtering** to remove tiny post-merge variants (`--select-min-size-ratio`)
+6. **Variant selection** within each group (`--select-max-variants`, `--select-strategy`)
+7. **Full consensus generation** (optional) — IUPAC consensus from all pre-merge variants per group (`--enable-full-consensus`)
+8. **Output generation** with customizable header fields (`--fasta-fields`) and full traceability
 
 **Key architectural features**:
 - HAC grouping occurs BEFORE merging to prevent inappropriate merging of dissimilar sequences (e.g., contaminants with primary targets)
@@ -1098,17 +1127,20 @@ usage: speconsense [-h] [-O OUTPUT_DIR] [--primers PRIMERS]
                    [--min-cluster-ratio MIN_CLUSTER_RATIO]
                    [--max-sample-size MAX_SAMPLE_SIZE]
                    [--outlier-identity OUTLIER_IDENTITY]
-                   [--disable-position-phasing]
+                   [--disable-position-phasing] [--enable-position-phasing]
                    [--min-variant-frequency MIN_VARIANT_FREQUENCY]
                    [--min-variant-count MIN_VARIANT_COUNT]
-                   [--disable-ambiguity-calling]
+                   [--disable-ambiguity-calling] [--enable-ambiguity-calling]
                    [--min-ambiguity-frequency MIN_AMBIGUITY_FREQUENCY]
                    [--min-ambiguity-count MIN_AMBIGUITY_COUNT]
-                   [--disable-cluster-merging]
+                   [--disable-cluster-merging] [--enable-cluster-merging]
                    [--disable-homopolymer-equivalence]
+                   [--enable-homopolymer-equivalence]
                    [--orient-mode {skip,keep-all,filter-failed}]
                    [--presample PRESAMPLE] [--scale-threshold SCALE_THRESHOLD]
-                   [--threads N] [--enable-early-filter] [--collect-discards]
+                   [--threads N] [--enable-early-filter]
+                   [--disable-early-filter] [--collect-discards]
+                   [--no-collect-discards]
                    [--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}]
                    [--version] [-p NAME] [--list-profiles]
                    input_file
@@ -1167,6 +1199,8 @@ Variant Phasing:
                         default). MCL graph clustering already separates most
                         variants; this second pass analyzes MSA positions to
                         phase remaining variants.
+  --enable-position-phasing
+                        Override --disable-position-phasing or profile setting
   --min-variant-frequency MIN_VARIANT_FREQUENCY
                         Minimum alternative allele frequency to call variant
                         (default: 0.10 for 10%)
@@ -1178,6 +1212,9 @@ Ambiguity Calling:
   --disable-ambiguity-calling
                         Disable IUPAC ambiguity code calling for unphased
                         variant positions
+  --enable-ambiguity-calling
+                        Override --disable-ambiguity-calling or profile
+                        setting
   --min-ambiguity-frequency MIN_AMBIGUITY_FREQUENCY
                         Minimum alternative allele frequency for IUPAC
                         ambiguity calling (default: 0.10 for 10%)
@@ -1189,9 +1226,14 @@ Cluster Merging:
   --disable-cluster-merging
                         Disable merging of clusters with identical consensus
                         sequences
+  --enable-cluster-merging
+                        Override --disable-cluster-merging or profile setting
   --disable-homopolymer-equivalence
                         Disable homopolymer equivalence in cluster merging
                         (only merge identical sequences)
+  --enable-homopolymer-equivalence
+                        Override --disable-homopolymer-equivalence or profile
+                        setting
 
 Orientation:
   --orient-mode {skip,keep-all,filter-failed}
@@ -1213,10 +1255,14 @@ Performance:
                         Enable early filtering to skip small clusters before
                         variant phasing (improves performance for large
                         datasets)
+  --disable-early-filter
+                        Override --enable-early-filter or profile setting
 
 Debugging:
   --collect-discards    Write discarded reads (outliers and filtered clusters)
                         to cluster_debug/{sample}-discards.fastq
+  --no-collect-discards
+                        Override --collect-discards or profile setting
   --log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}
 ```
 
@@ -1227,15 +1273,22 @@ usage: speconsense-summarize [-h] [--source SOURCE]
                              [--summary-dir SUMMARY_DIR]
                              [--fasta-fields FASTA_FIELDS] [--min-ric MIN_RIC]
                              [--min-len MIN_LEN] [--max-len MAX_LEN]
-                             [--group-identity GROUP_IDENTITY] [--merge-snp]
+                             [--group-identity GROUP_IDENTITY]
+                             [--disable-merging] [--enable-merging]
+                             [--merge-snp | --no-merge-snp]
                              [--merge-indel-length MERGE_INDEL_LENGTH]
                              [--merge-position-count MERGE_POSITION_COUNT]
                              [--merge-min-size-ratio MERGE_MIN_SIZE_RATIO]
                              [--min-merge-overlap MIN_MERGE_OVERLAP]
                              [--disable-homopolymer-equivalence]
+                             [--enable-homopolymer-equivalence]
+                             [--merge-effort LEVEL]
                              [--select-max-groups SELECT_MAX_GROUPS]
                              [--select-max-variants SELECT_MAX_VARIANTS]
                              [--select-strategy {size,diversity}]
+                             [--select-min-size-ratio SELECT_MIN_SIZE_RATIO]
+                             [--enable-full-consensus]
+                             [--disable-full-consensus]
                              [--scale-threshold SCALE_THRESHOLD] [--threads N]
                              [--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}]
                              [--version] [-p NAME] [--list-profiles]
@@ -1281,10 +1334,7 @@ Grouping:
 Merging:
   --disable-merging     Disable all variant merging (skip MSA-based merge
                         evaluation entirely)
-  --merge-effort LEVEL  Merging effort level: fast (8), balanced (10),
-                        thorough (12), or numeric 6-14. Higher values allow
-                        larger batch sizes for exhaustive subset search.
-                        Default: balanced
+  --enable-merging      Override --disable-merging or profile setting
   --merge-snp, --no-merge-snp
                         Enable SNP-based merging (default: True, use --no-
                         merge-snp to disable)
@@ -1303,6 +1353,13 @@ Merging:
   --disable-homopolymer-equivalence
                         Disable homopolymer equivalence in merging (treat AAA
                         vs AAAA as different)
+  --enable-homopolymer-equivalence
+                        Override --disable-homopolymer-equivalence or profile
+                        setting
+  --merge-effort LEVEL  Merging effort level: fast (8), balanced (10),
+                        thorough (12), or numeric 6-14. Higher values allow
+                        larger batch sizes for exhaustive subset search.
+                        Default: balanced
 
 Selection:
   --select-max-groups SELECT_MAX_GROUPS, --max-groups SELECT_MAX_GROUPS
@@ -1314,6 +1371,16 @@ Selection:
   --select-strategy {size,diversity}, --variant-selection {size,diversity}
                         Variant selection strategy: size or diversity
                         (default: size)
+  --select-min-size-ratio SELECT_MIN_SIZE_RATIO
+                        Minimum size ratio (variant/largest) to include in
+                        output (default: 0 = disabled, e.g. 0.2 for 20%
+                        cutoff)
+  --enable-full-consensus
+                        Generate a full consensus per variant group
+                        representing all variation from pre-merge variants
+                        (gaps never win)
+  --disable-full-consensus
+                        Override --enable-full-consensus or profile setting
 
 Performance:
   --scale-threshold SCALE_THRESHOLD

{speconsense-0.7.2.dist-info → speconsense-0.7.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-speconsense/__init__.py,sha256=VbusnaZk_gYhsif5UkANozOnjmCdNMDD_GOMPLfD5hQ,537
+speconsense/__init__.py,sha256=uLSZG2n0xobwuNT2PwZbytUg1DcyOr2aJlsbc52iKs0,537
 speconsense/cli.py,sha256=Kqb2da0IuazocAz72iqTnw71jI7UaQgxsHfb9CwiolU,85
 speconsense/msa.py,sha256=t1uDb-Tj5tDnB17QnNZPslpAiLXgAMIlnmMKBbwBKzs,31661
 speconsense/quality_report.py,sha256=Byrc115T03ybi7mpA0Bw8-gc83nhKPzDY0tyH1IIAMQ,19803
@@ -6,11 +6,12 @@ speconsense/synth.py,sha256=7kbifR9XZDcsB0wxo2PCHD8vLGEkVMTH3SQ724hTFGw,9892
 speconsense/types.py,sha256=_16nMMbfALEW212LDwTCan9u-gjvnS1ZQKpMK3y3zCE,1669
 speconsense/core/__init__.py,sha256=3AWfnmw1FTzzf-BRdGo1vRHjVJq7d-Wugsw50GJQY_0,694
 speconsense/core/__main__.py,sha256=dCfyQkVxxwlP6QqcWw9y5zp5iLzkG-fQsLmFHHEUlbI,112
-speconsense/core/cli.py,sha256=YmPj4CqjoFAyvgqXRZUFEjB7XAyUxho31rLKqBYw-yo,15767
+speconsense/core/cli.py,sha256=iepQMK0ZUhZvQShVZY_6WaHneR8ZIRKZ_b6NvVwaRwU,17186
 speconsense/core/clusterer.py,sha256=UFK5Ec0oMQ7l3GsFJOAhTFk7r90eOOdOBXRskm79Fwk,72093
 speconsense/core/workers.py,sha256=6pUyt-W9KxkillJ6TU1RjRh-_L-zRIwWqzIcBSeiOSc,25811
-speconsense/profiles/__init__.py,sha256=G2peTSx9xdFx0Z2nT71rTRHBwjWDxkFTdtGaQx-rujQ,16324
-speconsense/profiles/example.yaml,sha256=FGCsSAVtZL_m8PHWVLVrxaVCCwQkIk8wR7N7I2ZyxX0,4463
+speconsense/profiles/__init__.py,sha256=5UWj6VyUIXTzQ1kBZ4mJ2olZ_ADMK85rwr7KEmRfZfk,16382
+speconsense/profiles/compressed.yaml,sha256=LKtBm6nj8cpF2xeFcA7vzzNzaXdEo0JknnmcDDmdFj8,1227
+speconsense/profiles/example.yaml,sha256=UGHoVvFiB6iQ-lUU4rwInL6oE1eAd7Fo5qp14vfXJvA,4546
 speconsense/profiles/herbarium.yaml,sha256=1OyAPvBZmJ0eWHejfTU_NLd1_08F9n5WbeE686mzYGE,1125
 speconsense/profiles/largedata.yaml,sha256=7qwl5CHA7BiFcznycUoprOX_A-qrsZzV5fBLnA3QmcE,884
 speconsense/profiles/nostalgia.yaml,sha256=Hy20M88FiCmDvscyIKbwfNSusiHptmBm4pIWPiSFmp0,661
@@ -22,15 +23,15 @@ speconsense/scalability/vsearch.py,sha256=I1IzTeRzEFn9bi8mNbBRvtcHvUBzBFdE7D5yf-
 speconsense/summarize/__init__.py,sha256=PE6W9hytDxhkw7W6Fz8X3jd92N2VdhuxiQ72Nqm1xC0,3181
 speconsense/summarize/__main__.py,sha256=_hzLNqNtv4PirL1oMic37GW2QmjWquoznzNtld_3FiQ,117
 speconsense/summarize/analysis.py,sha256=1MXtKMpX1bgKEtI-JN6BwTQj99qyt1eQLqNg51EgPiE,31560
-speconsense/summarize/cli.py,sha256=Ptvt7D5Rwhg24_L_jqDI4xEb2ybRHoSEPC-c6a0K_yo,23281
+speconsense/summarize/cli.py,sha256=uSeY7__KpdQVXqJcQ0Zpn6ePeyJDVGdml7rZgHFr3W8,27124
 speconsense/summarize/clustering.py,sha256=kk-FdFCea8KRocowN_4dt_aoqZNVJMmEu7CVKPfYgK8,28346
-speconsense/summarize/fields.py,sha256=Mj7aUm4COU4niJeM6KG3R4c2SMD81lQNraDYWVh6CZ8,8550
-speconsense/summarize/io.py,sha256=Ofslc77qUDKB-9uFqdvjIPPZ0d0Tkjc_UsF0jwHWJZo,32220
+speconsense/summarize/fields.py,sha256=a6aK9hkPJ-sDRRSqM_7IkyqCki99KSMnsQMV-U7r2zY,8687
+speconsense/summarize/io.py,sha256=FdHLbcj0NOL3WE1e5OL85DRdJaHpyXPMcmlNg9mG3tM,32732
 speconsense/summarize/iupac.py,sha256=Y6KqELmnGy4Eya4C_4ldXY8uek0ReuSUgITLI3NW0-A,11042
-speconsense/summarize/merging.py,sha256=ptq6tJNplqHTf7U51Ppo2pGQkNF8ZTx-3kILT0Hbqxw,27754
-speconsense-0.7.2.dist-info/licenses/LICENSE,sha256=T_VYPNbu9NSWjdQunfk4jqUGND_kYWe_An18s6N492o,1498
-speconsense-0.7.2.dist-info/METADATA,sha256=1AlFCQ4kJ4_UKe3suOft55bF12gun1my0MyGqx2M5wg,75767
-speconsense-0.7.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-speconsense-0.7.2.dist-info/entry_points.txt,sha256=C0zFp5EYA8_KCb04uOyb4JNkxNH7bli1eU-XYrSX3BU,147
-speconsense-0.7.2.dist-info/top_level.txt,sha256=nYUJOHrqeX-OOxOYQKvpp7Iv8-Bed18wN1DBwWfJKnQ,12
-speconsense-0.7.2.dist-info/RECORD,,
+speconsense/summarize/merging.py,sha256=FakBey3qpu7ULPIsc2GDo9WG8jNU1L6q2pgQ2HrOKXk,28454
+speconsense-0.7.4.dist-info/licenses/LICENSE,sha256=T_VYPNbu9NSWjdQunfk4jqUGND_kYWe_An18s6N492o,1498
+speconsense-0.7.4.dist-info/METADATA,sha256=2vFyM5rqFEwMPIcsSAH32Dwh_bDA-bOk15D7El6MO7Y,79957
+speconsense-0.7.4.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+speconsense-0.7.4.dist-info/entry_points.txt,sha256=C0zFp5EYA8_KCb04uOyb4JNkxNH7bli1eU-XYrSX3BU,147
+speconsense-0.7.4.dist-info/top_level.txt,sha256=nYUJOHrqeX-OOxOYQKvpp7Iv8-Bed18wN1DBwWfJKnQ,12
+speconsense-0.7.4.dist-info/RECORD,,

{speconsense-0.7.2.dist-info → speconsense-0.7.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any